On MATH-500, adding IM improves or preserves every ESPO, GDPO, and SPG accuracy cell across generation lengths 128, 256, and 512. The largest printed relative gain is 6.10% for SPG+IM at length 512, where accuracy reaches 45.2%.

On MATH-500, adding IM improves or preserves every ESPO, GDPO, and SPG accuracy cell across generation lengths 128, 256, and 512. The largest printed relative gain is 6.10% for SPG+IM at length 512, where accuracy reaches 45.2%. · CiteArk

测量结果

已评估 0/36 项

获得支持 0有争议或冲突 0尚未评估 36

保留同一结论下的完整结果组。已有评估排在前面；单项判断不替代整组结论。展开行查看条件、来源与历次证据。

每行是一项测量，分别显示论文报告、最近可用实测和累计证据状态。
指标与条件	论文报告	最近可用实测	证据判断
model: LLaDA-8B-Instruct · dataset: MATH-500 · generationLengthTokens: 128	26%	—	尚未评估
model: LLaDA-8B-Instruct · dataset: MATH-500 · generationLengthTokens: 256	32.4%	—	尚未评估
model: LLaDA-8B-Instruct · dataset: MATH-500 · generationLengthTokens: 512	36.2%	—	尚未评估
model: D1 · dataset: MATH-500 · generationLengthTokens: 128	31.4%	—	尚未评估
model: D1 · dataset: MATH-500 · generationLengthTokens: 256	36%	—	尚未评估
model: D1 · dataset: MATH-500 · generationLengthTokens: 512	39.4%	—	尚未评估
model: WD1 · dataset: MATH-500 · generationLengthTokens: 128	31%	—	尚未评估
model: WD1 · dataset: MATH-500 · generationLengthTokens: 256	34.4%	—	尚未评估
model: WD1 · dataset: MATH-500 · generationLengthTokens: 512	39%	—	尚未评估
model: ESPO · dataset: MATH-500 · generationLengthTokens: 128	35.2%	—	尚未评估
model: ESPO · dataset: MATH-500 · generationLengthTokens: 256	37.8%	—	尚未评估
model: ESPO · dataset: MATH-500 · generationLengthTokens: 512	37.6%	—	尚未评估

On MATH-500, adding IM improves or preserves every ESPO, GDPO, and SPG accuracy cell across generation lengths 128, 256, and 512. The largest printed relative gain is 6.10% for SPG+IM at length 512, where accuracy reaches 45.2%.

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果